© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 10119
    Prev
    Next
    INDEX
    Explanations

    elements related to programming functions and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.50
    transQ
    -0.47
    AddTagHelper
    -0.46
    NameInMap
    -0.42
     rootReducer
    -0.41
    numerusform
    -0.40
    StoryboardSegue
    -0.40
     einzigen
    -0.39
    WriteBarrier
    -0.38
    طلحات
    -0.38
    POSITIVE LOGITS
     name
    0.65
     flags
    0.65
     type
    0.65
     kind
    0.61
     owner
    0.60
    kind
    0.56
     weight
    0.55
     Flags
    0.54
     belongs
    0.54
     attributes
    0.54
    Activations Density 1.202%

    No Known Activations